What does the term 'familywise error rate' refer to?

• A. At least one Type II error across tests.
• B. The likelihood that all null hypotheses are true.
• C. At least one Type I error across tests.
• D. The average p-value across tests.

Answer: (C)

Familywise error rate is the probability of making at least one false positive (Type I error) across a set of tests. When you run many statistical tests, the chance that at least one test incorrectly rejects a true null hypothesis grows. For example, with 20 independent tests at α = 0.05, the FWER is 1 − (1 − 0.05)²⁰ ≈ 0.64, meaning a 64% chance of at least one false positive somewhere in the set. To keep this risk manageable, researchers use corrections like Bonferroni or Holm-Bonferroni that adjust the criteria for individual tests to control the overall FWER. The other options don’t capture this idea: one refers to missing real effects (Type II error), another to the probability that all nulls are true, and the last to the average p-value, none of which define the familywise error concept.